Marathi Tweet Sentiment Classification: TF-IDF Baselines versus Fine-tuned MuRIL and MahaBERT
Year: 2026
Type: preprint
Abstract: We compare classical and transformer-based approaches for three-class sentimentclassification (negative, neutral, positive) of Marathi tweets on the L3CubeMahaSentdataset. TF-IDF baselines with logistic regression and a linear SVM reach test macro-F1 of0.752 and 0.745. Fine-tuning the multilingual MuRIL and the Marathi-specific MahaBERTimproves this to 0.842 and 0.855 (mean over three seeds), a gain of roughly 9 to 11 points.MahaBERT outperforms MuRIL on average, but the difference is modest: it is statisticallysignificant for one of three seed pairs (McNemar, p < 0.001), borderline for another (p =0.049) and not significant for the third (p = 0.123). In both models, 83 to 85% of errorsinvolve the neutral class. An exploratory second-pass review of 50 misclassified neutraltweets, which we could not verify with human annotators, suggests that many sit at anambiguous boundary in the annotation guidelines, which may limit attainable accuracy.
Author: Sathe, Yash
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7223471745
Cites:
Cited by:
Related to: